13 papers · 1 filter
Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation under Embodiment Mismatch
Yoshiki Takebayashi, Giovanni Perantoni, Hikaru Sasaki +2
With the increasing use of robot-free demonstration interfaces that provide state trajectories without action labels, imitation from observation has become a promising approach for…
quARtet Marker: A 3D-Printable Multi-Tag Fiducial for Robust Near-Frontal Pose Estimation
Araki Wakiuchi, Hikaru Sasaki, Takamitsu Matsubara
Robotic manipulation of labware is difficult when transparent or reflective objects must be identified and localized. Coded planar fiducials are a practical retrofit: easy to print…
Task-Relevant and Irrelevant Region-Aware Augmentation for Generalizable Vision-Based Imitation Learning in Agricultural Manipulation
Shun Hattori, Hikaru Sasaki, Takumi Hachimine +2
Vision-based imitation learning has shown promise for robotic manipulation; however, its generalization remains limited in practical agricultural tasks. This limitation stems from…
Feasibility-aware Imitation Learning from Observation with Multimodal Feedback
Kei Takahashi, Hikaru Sasaki, Takamitsu Matsubara
Imitation learning frameworks that learn robot control policies from demonstrators' motions via hand-mounted demonstration interfaces have attracted increasing attention. However,…
Robotic System for Chemical Experiment Automation with Dual Demonstration of End-effector and Jig Operations
Hikaru Sasaki, Naoto Komeno, Takumi Hachimine +9
While robotic automation has demonstrated remarkable performance, such as executing hundreds of experiments continuously over several days, designing synchronized motions between t…
Feasibility-aware Imitation Learning from Observations through a Hand-mounted Demonstration Interface
Kei Takahashi, Hikaru Sasaki, Takamitsu Matsubara
Imitation learning through a demonstration interface is expected to learn policies for robot automation from intuitive human demonstrations. However, due to the differences in huma…
Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies
Shu-yuan Wang, Hikaru Sasaki, Takamitsu Matsubara
Learning control policies for real-world robotic tasks often involve challenges such as multimodality, local discontinuities, and the need for computational efficiency. These chall…
Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks
Hirotaka Tahara, Hikaru Sasaki, Hanbit Oh +2
Partial Automation (PA) with intelligent support systems has been introduced in industrial machinery and advanced automobiles to reduce the burden of long hours of human operation.…
Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation
Hanbit Oh, Hikaru Sasaki, Brendan Michael +1
Humans demonstrate a variety of interesting behavioral characteristics when performing tasks, such as selecting between seemingly equivalent optimal actions, performing recovery ac…
Disturbance-Injected Robust Imitation Learning with Task Achievement
Hirotaka Tahara, Hikaru Sasaki, Hanbit Oh +2
Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that p…
Gaussian Process Self-triggered Policy Search in Weakly Observable Environments
Hikaru Sasaki, Terushi Hirabayashi, Kaoru Kawabata +1
The environments of such large industrial machines as waste cranes in waste incineration plants are often weakly observable, where little information about the environmental state…
Variational Policy Search using Sparse Gaussian Process Priors for Learning Multimodal Optimal Actions
Hikaru Sasaki, Takamitsu Matsubara
Policy search reinforcement learning has been drawing much attention as a method of learning a robot control policy. In particular, policy search using such non-parametric policies…
Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies
Hanbit Oh, Hikaru Sasaki, Brendan Michael +1
Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an…